Alpha band modulation caused by selective attention to music enables EEG classification.

Humans are able to pay selective attention to music or speech in the presence of multiple sounds. It has been reported that in the speech domain, selective attention enhances the cross-correlation between the envelope of speech and electroencephalogram (EEG) while also affecting the spatial modulation of the alpha band. However, when multiple music pieces are performed at the same time, it is unclear how selective attention affects neural entrainment and spatial modulation. In this paper, we hypothesized that the entrainment to the attended music differs from that to the unattended music and that spatial modulation in the alpha band occurs in conjunction with attention. We conducted experiments in which we presented musical excerpts to 15 participants, each listening to two excerpts simultaneously but paying attention to one of the two. The results showed that the cross-correlation function between the EEG signal and the envelope of the unattended melody had a more prominent peak than that of the attended melody, contrary to the findings for speech. In addition, the spatial modulation in the alpha band was found with a data-driven approach called the common spatial pattern method. Classification of the EEG signal with a support vector machine identified attended melodies and achieved an accuracy of 100% for 11 of the 15 participants. These results suggest that selective attention to music suppresses entrainment to the melody and that spatial modulation of the alpha band occurs in conjunction with attention. To the best of our knowledge, this is the first report to detect attended music consisting of several types of music notes only with EEG.

Preparation of Waterborne Silicone-Modified Polyurethane Nanofibers and the Effect of Crosslinking Agents on Physical Properties.

Silicone-modified polyurethane (PUSX) refers to the introduction of a silicone short chain into the polyurethane chain to make it have the dual properties of silicone and polyurethane (PU). It can be used in many fields, such as coatings, films, molding products, adhesives, and so on. The use of organic solvents to achieve the fiberization of silicone-modified polyurethane has been reported. However, it is challenging to achieve the fiberization of silicone-modified polyurethane based on an environmentally friendly water solvent. Herein, we report a simple and powerful strategy to fabricate environmentally friendly waterborne silicone-modified polyurethane nanofiber membranes through the addition of polyethylene glycol (PEG) with different molecular weights using electrospinning technology and in situ doping with three crosslinking agents with different functional groups (a polyoxazoline crosslinking agent, a polycarbodiimide crosslinking agent, and a polyisocyanate crosslinking agent) combined with various heating treatment conditions. The influence of PEG molecular weight on fiber formation was explored. The morphology, structure, water resistance, and mechanical properties were analyzed regarding the effect of the introduction of silicone into PU. The effects of the type and content of crosslinking agent on the morphology and physical properties of PUSX nanofiber membranes are discussed. These results show that the introduction of silicone can improve the water resistance and high temperature resistance of waterborne PU, and the addition of a crosslinking agent can further improve the water resistance of the sample, so that the sample can maintain good morphology after immersion. Crosslinking agents with different functional groups had different effects on the mechanical properties of PUSX nanofiber membranes due to different reactions. Among them, the oxazoline crosslinking agent had a significant effect on improving tensile strength, while the isocyanate crosslinking agent had a significant effect on improving the elongation at break. The PUSX nanofiber membrane prepared in this work did not use organic solvents that were harmful to humans and the environment, and it can be used in outdoor textiles, oil-water separation, medical health, and other fields.

Fabrication of Waterborne Silicone-Modified Polyurethane Nanofibers for Nonfluorine Elastic Waterproof and Breathable Membranes.

Waterproof and breathable membranes have a huge market demand in areas, such as textiles and medical protection. However, existing fluorinated nanofibrous membranes, while possessing good waterproof and breathable properties, pose health and environmental hazards. Consequently, fabricating fluorine-free, eco-friendly waterborne membranes by integrating outstanding waterproofing, breathability, and robust mechanical performance remains a significant challenge. Herein, we successfully prepared waterborne silicone-modified polyurethane nanofibrous membranes with excellent elasticity, waterproofing, and breathability properties through waterborne electrospinning, using a small quantity of poly(ethylene oxide) as a template polymer and in situ doping of the poly(carbodiimide) crosslinking agent, followed by a simple hot-pressing treatment. The silicone imparted the nanofibrous membrane with high hydrophobicity, and the crosslinking agent enabled its stable porous structure. The hot-pressing treatment (120 °C) further reduced the pore size and improved the water resistance. This environmentally friendly nanofibrous membrane showed a high elongation at break of 428%, an ultra-high elasticity of 67.5% (160 cycles under 400% tensile strain), an air transmission of 13.2 mm s-1, a water vapor transmission rate of 5476 g m-2 d-1, a hydrostatic pressure of 51.5 kPa, and a static water contact angle of 137.9°. The successful fabrication of these environmentally friendly, highly elastic membranes provides an important reference for applications in healthcare, protective textiles, and water purification.

Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech.

Several attempts for speech brain-computer interfacing (BCI) have been made to decode phonemes, sub-words, words, or sentences using invasive measurements, such as the electrocorticogram (ECoG), during auditory speech perception, overt speech, or imagined (covert) speech. Decoding sentences from covert speech is a challenging task. Sixteen epilepsy patients with intracranially implanted electrodes participated in this study, and ECoGs were recorded during overt speech and covert speech of eight Japanese sentences, each consisting of three tokens. In particular, Transformer neural network model was applied to decode text sentences from covert speech, which was trained using ECoGs obtained during overt speech. We first examined the proposed Transformer model using the same task for training and testing, and then evaluated the model's performance when trained with overt task for decoding covert speech. The Transformer model trained on covert speech achieved an average token error rate (TER) of 46.6% for decoding covert speech, whereas the model trained on overt speech achieved a TER of 46.3% ( p > 0.05 ; d = 0.07 ) . Therefore, the challenge of collecting training data for covert speech can be addressed using overt speech. The performance of covert speech can improve by employing several overt speeches.

Causal Connectivity Network Analysis of Ictal Electrocorticogram With Temporal Lobe Epilepsy Based on Dynamic Phase Transfer Entropy.

Temporallobe epilepsy (TLE) has been conceptualized as a brain network disease, which generates brain connectivity dynamics within and beyond the temporal lobe structures in seizures. The hippocampus is a representative epileptogenic focus in TLE. Understanding the causal connectivity in terms of brain network during seizures is crucial in revealing the triggering mechanism of epileptic seizures originating from the hippocampus (HPC) spread to the lateral temporal cortex (LTC) by ictal electrocorticogram (ECoG), particularly in high-frequency oscillations (HFOs) bands. In this study, we proposed the unified-epoch dynamic causality analysis method to investigate the causal influence dynamics between two brain regions (HPC and LTC) at interictal and ictal phases in the frequency range of 1-500 Hz by introducing the phase transfer entropy (PTE) out/in-ratio and sliding window. We also proposed PTE-based machine learning algorithms to identify epileptogenic zone (EZ). Nine patients with a total of 26 seizures were included in this study. We hypothesized that: 1) HPC is the focus with the stronger causal connectivity than that in LTC in the ictal state at gamma and HFOs bands. 2) Causal connectivity in the ictal phase shows significant changes compared to that in the interictal phase. 3) The PTE out/in-ratio in the HFOs band can identify the EZ with the best prediction performance.

Modeling Complex EEG Data Distribution on the Riemannian Manifold Toward Outlier Detection and Multimodal Classification.

OBJECTIVE: The usage of Riemannian geometry for Brain-computer interfaces (BCIs) has gained momentum in recent years. Most of the machine learning techniques proposed for Riemannian BCIs consider the data distribution on a manifold to be unimodal. However, the distribution is likely to be multimodal rather than unimodal since high-data variability is a crucial limitation of electroencephalography (EEG). In this paper, we propose a novel data modeling method for considering complex data distributions on a Riemannian manifold of EEG covariance matrices, aiming to improve BCI reliability. METHODS: Our method, Riemannian spectral clustering (RiSC), represents EEG covariance matrix distribution on a manifold using a graph with proposed similarity measurement based on geodesic distances, then clusters the graph nodes through spectral clustering. This allows flexibility to model both a unimodal and a multimodal distribution on a manifold. RiSC can be used as a basis to design an outlier detector named outlier detection Riemannian spectral clustering (odenRiSC) and a multimodal classifier named multimodal classifier Riemannian spectral clustering (mcRiSC). All required parameters of odenRiSC/mcRiSC are selected in data-driven manner. Moreover, there is no need to pre-set a threshold for outlier detection and the number of modes for multimodal classification. RESULTS: The experimental evaluation revealed odenRiSC can detect EEG outliers more accurately than existing methods and mcRiSC outperformed the standard unimodal classifier, especially on high-variability datasets. CONCLUSION: odenRiSC/mcRiSC are anticipated to contribute to making real-life BCIs outside labs and neuroergonomics applications more robust. SIGNIFICANCE: RiSC can work as a robust EEG outlier detector and multimodal classifier.

Nonparametric tensor ring decomposition with scalable amortized inference.

Multi-dimensional data are common in many applications, such as videos and multi-variate time series. While tensor decomposition (TD) provides promising tools for analyzing such data, there still remains several limitations. First, traditional TDs assume multi-linear structures of the latent embeddings, which greatly limits their expressive power. Second, TDs cannot be straightforwardly applied to datasets with massive samples. To address these issues, we propose a nonparametric TD with amortized inference networks. Specifically, we establish a non-linear extension of tensor ring decomposition, using neural networks, to model complex latent structures. To jointly model the cross-sample correlations and physical structures, a matrix Gaussian process (GP) prior is imposed over the core tensors. From learning perspective, we develop a VAE-like amortized inference network to infer the posterior of core tensors corresponding to new tensor data, which enables TDs to be applied to large datasets. Our model can be also viewed as a kind of decomposition of VAE, which can additionally capture hidden tensor structure and enhance the expressiveness power. Finally, we derive an evidence lower bound such that a scalable optimization algorithm is developed. The advantages of our method have been evaluated extensively by data imputation on the Healing MNIST dataset and four multi-variate time series data.

Identification of Seizure Onset Zone from Intracranial EEG Using Source Selection-Based Domain Adaptation.

For focal epilepsy patients, correctly identifying the seizure onset zone (SOZ) is essential for surgical treatment. In automated realistic SOZ identification, it is necessary to identify the SOZ of an unknown patient using another patient's electroencephalogram (EEG). However, in such cases, the influence of individual differences in EEG becomes a bottleneck. In this paper, we propose the method with domain adaptation and source patient selection to address the issue of individual differences in EEG and improve performance. The proposed method was evaluated on intracranial EEG data from 11 patients with epilepsy caused by focal cortical dysplasia. The results showed that the proposed method significantly improved SOZ identification performance compared to existing methods without domain adaptation and source patient selection. In addition, it was suggested that data from residual-seizure patients may have adversely affected estimation performance. Visualization of the prediction on MRI images showed that the proposed method might detect SOZs missed by epileptologists.

Video stimuli suitable for stress estimation based on biosignals.

Stress can cause mental disorders such as depression and anxiety disorders. To detect such mental disorders at an early stage, it is necessary to detect stress accurately. One of the effective methods for this purpose is observing changes in biological signals caused by sensory stimuli such as video presentation. This study aims to identify effective video stimuli for stress estimation. We hypothesize that the emotional state evoked by the video stimuli influences the accuracy of stress estimation. To test this hypothesis, we utilized an open video dataset consisting of 444 responses on an emotion scale (valence and arousal) as emotional stimuli. Ninety videos were divided into emotion subsets based on the emotion scale for each video, and biological signals were measured when each video was presented to the subjects. Machine learning models were constructed for each subset, and the prediction errors were compared. The results showed that the prediction error was lower for the high valence and high arousal subsets than for the others. These results suggest that high-valence or high-arousal videos effectively estimate stress.

Special Issue "Machine Learning Methods for Biomedical Data Analysis".

Machine learning is an effective method for developing automatic algorithms for analysing sophisticated biomedical data [...].

Seizure onset zone identification using phase-amplitude coupling and multiple machine learning approaches for interictal electrocorticogram.

Automatic seizure onset zone (SOZ) localization using interictal electrocorticogram (ECoG) improves the diagnosis and treatment of patients with medically refractory epilepsy. This study aimed to investigate the characteristics of phase-amplitude coupling (PAC) extracted from interictal ECoG and the feasibility of PAC serving as a promising biomarker for SOZ identification. We employed the mean vector length modulation index approach on the 20-s ECoG window to calculate PAC features between low-frequency rhythms (0.5-24 Hz) and high frequency oscillations (HFOs) (80-560 Hz). We used statistical measures to test the significant difference in PAC between the SOZ and non-seizure onset zone (NSOZ). To overcome the drawback of handcraft feature engineering, we established novel machine learning models to learn automatically the characteristics of the obtained PAC features and classify them to identify the SOZ. Besides, to handle imbalanced dataset classification, we introduced novel feature-wise/class-wise re-weighting strategies in conjunction with classifiers. In addition, we proposed a time-series nest cross-validation to provide more accurate and unbiased evaluations for this model. Seven patients with focal cortical dysplasia were included in this study. The experiment results not only showed that a significant coupling at band pairs of slow waves and HFOs exists in the SOZ when compared with the NSOZ, but also indicated the effectiveness of the PAC features and the proposed models in achieving better classification performance .

Classification of the Epileptic Seizure Onset Zone Based on Partial Annotation.

Epilepsy is a chronic disorder caused by excessive electrical discharges. Currently, clinical experts identify the seizure onset zone (SOZ) channel through visual judgment based on long-time intracranial electroencephalogram (iEEG), which is a very time-consuming, difficult and experience-based task. Therefore, there is a need for high-accuracy diagnostic aids to reduce the workload of clinical experts. In this article, we propose a method in which, the iEEG is split into the 20-s segment and for each patient, we ask clinical experts to label a part of the data, which is used to train a model and classify the remaining iEEG data. In recent years, machine learning methods have been successfully applied to solve some medical problems. Filtering, entropy and short-time Fourier transform (STFT) are used for extracting features. We compare them to wavelet transform (WT), empirical mode decomposition (EMD) and other traditional methods with the aim of obtaining the best possible discriminating features. Finally, we look for their medical interpretation, which is important for clinical experts. We achieve high-performance results for SOZ and non-SOZ data classification by using the labeled iEEG data and support vector machine (SVM), fully connected neural network (FCNN) and convolutional neural network (CNN) as classification models. In addition, we introduce the positive unlabeled (PU) learning to further reduce the workload of clinical experts. By using PU learning, we can learn a binary classifier with a small amount of labeled data and a large amount of unlabeled data. This can greatly reduce the amount and difficulty of annotation work by clinical experts. All together, we show that using 105 minutes of labeled data we achieve a classification result of 91.46% on average for multiple patients.

Chronological changes in phase-amplitude coupling during epileptic seizures in temporal lobe epilepsy.

OBJECTIVE: To analyze chronological changes in phase-amplitude coupling (PAC) and verify whether PAC analysis can diagnose epileptogenic zones during seizures. METHODS: We analyzed 30 seizures in 10 patients with mesial temporal lobe epilepsy who had ictal discharges with preictal spiking followed by low-voltage fast activity patterns on intracranial electroencephalography. We used the amplitude of two high-frequency bands (ripples: 80-200 Hz, fast ripples: 200-300 Hz) and the phase of three slow wave bands (0.5-1 Hz, 3-4 Hz, and 4-8 Hz) for modulation index (MI) calculation from 2 minutes before seizure onset to seizure termination. We evaluated the accuracy of epileptogenic zone detection by MI, in which a combination of MI was better for diagnosis and analyzed patterns of chronological changes in MI during seizures. RESULTS: MIRipples/3-4 Hz and MIRipples/4-8 Hz in the hippocampus were significantly higher than those in the peripheral regions from seizure onset. Corresponding to the phase on intracranial electroencephalography, MIRipples/3-4 Hz decreased once and subsequently increased again. MIRipples/4-8 Hz showed continuously high values. CONCLUSIONS: Continuous measurement of MIRipples/3-4 Hz and MIRipples/4-8 Hz could help identify epileptogenic zones. SIGNIFICANCE: PAC analysis of ictal epileptic discharges can help epileptogenic zone identification.

Epileptic seizure detection by using interpretable machine learning models.

Objective.Accurate detection of epileptic seizures using electroencephalogram (EEG) data is essential for epilepsy diagnosis, but the visual diagnostic process for clinical experts is a time-consuming task. To improve efficiency, some seizure detection methods have been proposed. Regardless of traditional or machine learning methods, the results identify only seizures and non-seizures. Our goal is not only to detect seizures but also to explain the basis for detection and provide reference information to clinical experts.Approach.In this study, we follow the visual diagnosis mechanism used by clinical experts that directly processes plotted EEG image data and apply some commonly used models of LeNet, VGG, deep residual network (ResNet), and vision transformer (ViT) to the EEG image classification task. Before using these models, we propose a data augmentation method using random channel ordering (RCO), which adjusts the channel order to generate new images. The Gradient-weighted class activation mapping (Grad-CAM) and attention layer methods are used to interpret the models.Main results.The RCO method can balance the dataset in seizure and non-seizure classes. The models achieved good performance in the seizure detection task. Moreover, the Grad-CAM and attention layer methods explained the detection basis of the model very well and calculate a value that measures the seizure degree.Significance.Processing EEG data in the form of images can flexibility to use a variety of machine learning models. The imbalance problem that exists widely in clinical practice is well solved by the RCO method. Since the method follows the visual diagnosis mechanism of clinical experts, the model interpretation results can be presented to clinical experts intuitively, and the quantitative information provided by the model is also a good diagnostic reference.

Epileptic seizure focus detection from interictal electroencephalogram: a survey.

Electroencephalogram (EEG) is one of most effective clinical diagnosis modalities for the localization of epileptic focus. Most current AI solutions use this modality to analyze the EEG signals in an automated manner to identify the epileptic seizure focus. To develop AI system for identifying the epileptic focus, there are many recently-published AI solutions based on biomarkers or statistic features that utilize interictal EEGs. In this review, we survey these solutions and find that they can be divided into three main categories: (i) those that use of biomarkers in EEG signals, including high-frequency oscillation, phase-amplitude coupling, and interictal epileptiform discharges, (ii) others that utilize feature-extraction methods, and (iii) solutions based upon neural networks (an end-to-end approach). We provide a detailed description of seizure focus with clinical diagnosis methods, a summary of the public datasets that seek to reduce the research gap in epilepsy, recent novel performance evaluation criteria used to evaluate the AI systems, and guidelines on when and how to use them. This review also suggests a number of future research challenges that must be overcome in order to design more efficient computer-aided solutions to epilepsy focus detection.

Cerebrospinal fluid amyloid beta and response of cognition to a tap test in idiopathic normal pressure hydrocephalus: a case-control study.

OBJECTIVES: To examine the relationship between cerebrospinal fluid (CSF) biomarkers of Alzheimer's disease (AD) and tap test response to elucidate the effects of comorbidity of AD in idiopathic normal-pressure hydrocephalus (iNPH). DESIGN: Case-control study. SETTING: Osaka University Hospital. PARTICIPANTS: Patients with possible iNPH underwent a CSF tap test. MEASUREMENTS: Concentrations of amyloid beta (Aß) 1-40, 1-42, and total tau in CSF were measured. The response of tap test was judged using Timed Up and Go test (TUG), 10-m reciprocation walking test (10MWT), Mini-Mental State Examination (MMSE), and iNPH grading scale. The ratio of Aß1-42 to Aß1-40 (Aß42/40 ratio) and total tau concentration was compared between tap test-negative (iNPH-nTT) and -positive (iNPH-pTT) patients. RESULTS: We identified 27 patients as iNPH-nTT and 81 as iNPH-pTT. Aß42/40 ratio was significantly lower (mean [SD] = 0.063 [0.026] vs. 0.083 [0.036], p = 0.008), and total tau in CSF was significantly higher (mean [SD] = 385.6 [237.2] vs. 293.6 [165.0], p = 0.028) in iNPH-nTT than in iNPH-pTT. Stepwise logistic regression analysis revealed that low Aß42/40 ratio was significantly associated with the negativity of the tap test. The response of cognition was significantly related to Aß42/40 ratio. The association between Aß42/40 ratio and tap test response, especially in cognition, remained after adjusting for disease duration and severity at baseline. CONCLUSIONS: A low CSF Aß42/40 ratio is associated with a poorer cognitive response, but not gait and urinary response, to a tap test in iNPH. Even if CSF biomarkers suggest AD comorbidity, treatment with iNPH may be effective for gait and urinary dysfunction.

Seizure onset zone classification based on imbalanced iEEG with data augmentation.

Objective. Identifying the seizure onset zone (SOZ) in patients with focal epilepsy is the critical information required for surgery. However, collecting this information is challenging, time-consuming, and subjective. Some machine learning methods reduce the workload of clinical experts in intracranial electroencephalogram (iEEG) visual diagnosis but face significant challenges because interictal iEEG clinical data often suffer from a significant class imbalance. We aim to generate synthetic data for the minority class.Approach. To make the clinically imbalanced data suitable for machine learning, we introduce an EEG augmentation method (EEGAug). The EEGAug method randomly selects several samples from the minority class and transforms them into the frequency domain. Then, different frequency bands from different samples are used to compose new data. Finally, a synthetic sample is generated after converting the new data back to the time domain.Main results. The imbalanced clinical iEEG data can be balanced and applied to machine learning models using the method. A one-dimensional convolutional neural network model is used to classify the SOZ and non-SOZ data. We compare the EEGAug method with other data augmentation methods and another method of class-balanced focal loss function, which is also used for solving the data imbalance problem by adjusting the weights between the minority and majority classes. The results show that the EEGAug method performs best in most data.Significance. Data imbalance is a widespread clinical problem. The EEGAug method can flexibly generate synthetic data for the minority class, yielding synthetic and raw data with a high distribution similarity. By using the EEGAug method, clinical data can be used in machine learning models.

Satelight: self-attention-based model for epileptic spike detection from multi-electrode EEG.

Objective.Because of the lack of highly skilled experts, automated technologies that support electroencephalogram (EEG)-based in epilepsy diagnosis are advancing. Deep convolutional neural network-based models have been used successfully for detecting epileptic spikes, one of the biomarkers, from EEG. However, a sizeable number of supervised EEG records are required for training.Approach.This study introduces the Satelight model, which uses the self-attention (SA) mechanism. The model was trained using a clinical EEG dataset labeled by five specialists, including 16 008 epileptic spikes and 15 478 artifacts from 50 children. The SA mechanism is expected to reduce the number of parameters and efficiently extract features from a small amount of EEG data. To validate the effectiveness, we compared various spike detection approaches with the clinical EEG data.Main results.The experimental results showed that the proposed method detected epileptic spikes more effectively than other models (accuracy = 0.876 and false positive rate = 0.133).Significance.The proposed model had only one-tenth the number of parameters as the other effective model, despite having such a high detection performance. Further exploration of the hidden parameters revealed that the model automatically attended to the EEG's characteristic waveform locations of interest.

Higher phase-amplitude coupling between ripple and slow oscillations indicates the distribution of epileptogenicity in temporal lobe epilepsy with hippocampal sclerosis.

OBJECTIVE: We assessed the diagnostic utility of the occurrence rate of high-frequency oscillations and modulation index (MI) from intraoperative electrocorticography (ioECoG) in determining the extent of epileptogenicity in mesial temporal lobe epilepsy (TLE) with hippocampal sclerosis (HS). METHODS: We enrolled 17 patients who underwent selective amygdalohippocampectomy (SelAH) for TLE due to HS. We analyzed the occurrence rate of ripples (80-200 Hz) and fast ripples (200-300 Hz); and MI between ripples and 3-4 Hz (MIRipples/3-4 Hz) and fast ripples and 3-4 Hz (MIFRs/3-4 Hz) from the amygdala, hippocampus, and lateral temporal lobe (LTL) pre-SelAH and the LTL post-SelAH, and subsequently categorized the patients into good and poor seizure outcome groups. We compared the occurrence rates and MIs over each region of interest between both groups. Receiver operating characteristic analysis was used to identify the most optimal indicator to predict poor surgical outcomes. RESULTS: In the poor seizure outcome group, an increase in the occurrence rate of ripples was seen in the hippocampus and LTL pre-SelAH and the LTL post-SelAH. The MIRipples/3-4 Hz from the LTL pre-SelAH was the most indicative factor of poor outcome. CONCLUSIONS: High occurrence rate of ripples and MIRipples/3-4 Hz from the LTL showed wide epileptogenicity in TLE patients with poor seizure outcomes after SelAH. Our data suggest that the analysis of the occurrence rate of HFOs and MIHFOs/3-4 Hz from ioECoG, especially from the LTL, can indicate the distribution of epileptogenicity in TLE with HS.